Recently, contrastive learning attracts increasing interests in neural text generation as a new
solution to alleviate the exposure bias problem. It introduces a sequence-level training …

We show that learners generalized more broadly around the learned stimulus when they
expected more variability between the learning set and the generalization set, as well as …

The diversity principle—the intuitive notion that diverse evidence is, all else equal, more
persuasive, suggestive, confirmatory, or otherwise better than less varied sets of evidence …

Humans often generalize rewarding experiences across abstract social roles. Theories of
reward learning suggest that people generalize through model-based learning, but such …

Abstract Automatically Impression Generation (AIG) can conclude essential information of
the “Findings” section, thus facilitating more effective communication between radiographers …

Category learning is essential for making sense of the complex world around us. Unlike
traditional laboratory settings, real-world learning often allows individuals to self-regulate …

In property induction tasks, encountering a diverse range of instances (eg, hippos and
hamsters) with a given property usually increases our willingness to generalise that property …

Previous work on empathetic response generation mainly focused on utilizing the speaker's
emotions to generate responses. However, the performance of identifying fine-grained …

The diversity effect during category‐based induction (CBI) means that the more diverse the
evidence, the higher will be the conclusion's inductive strength. However, it is influenced by …

In property induction tasks, encountering a diverse range of instances (eg, hippos and
hamsters) with a given property usually increases our willingness to generalize that property …